Unsupervised Learning of the Morphology of a Natural Language
Unsupervised Learning of the Morphology of a Natural Language
复制标题
DOI：
10.1162/089120101750300490
复制
发表时间：
2001-06
影响因子：
9.3
通讯作者：
J. Goldsmith
中科院分区：
文献类型：
--
作者：
J. Goldsmith
这项研究报告了使用最小描述长度（MDL）分析来模拟欧洲语言形态分割的无监督学习的结果，使用的语料库大小从5，000个单词到500，000个单词。我们开发了一套快速发展的概率形态语法，并使用MDL作为我们的主要工具，以确定是否将通过或不采用的prostitics提出的修改。由此产生的语法与人类形态学家开发的分析很好地匹配。在最后一节中，我们讨论了这种风格的MDL语法分析的早期生成语法的评价度量的概念的关系。
This study reports the results of using minimum description length (MDL) analysis to model unsupervised learning of the morphological segmentation of European languages, using corpora ranging in size from 5,000 words to 500,000 words. We develop a set of heuristics that rapidly develop a probabilistic morphological grammar, and use MDL as our primary tool to determine whether the modifications proposed by the heuristics will be adopted or not. The resulting grammar matches well the analysis that would be developed by a human morphologist. In the final section, we discuss the relationship of this style of MDL grammatical analysis to the notion of evaluation metric in early generative grammar.